NVIDIA’s Axolotl3D unifies 3D completion, editing, and extraction in one model
NVIDIA Developer · youtube · 2026-07-29
Axolotl3D unifies several 3D tasks in one model
NVIDIA Research introduced Axolotl3D, a unified 3D generation model that can complete objects from partial observations such as images, visibility masks, and point clouds.
- Handles multi-view image-to-3D, occlusion completion, local shape editing, and object extraction from Gaussian Splat scenes in a single model.
- The model is trained by simulating diverse partial observations from large-scale 3D data.
- The work has been accepted to ECCV 2026.
The project page and paper are both public.
Related event: NVIDIA Introduces Axolotl3D for Unified 3D Completion(2 posts)→
More from Multimodal
- 1,290-line commit lands MOSS Image support in ostris/ai-toolkit — ostrisai · 2026-10-16
- Ostris AI Toolkit adds training support for OpenMOSS's MOSS-Image-SFT model — ostrisai · 2026-10-16
- Nokia vs iPhone, car edition: AI image shows Tesla Roadster hovering over a Porsche — vaibhavbetter · 2026-10-16
- Midjourney multi-sref weight mixing recipe for cinematic light & motion portraits — michaelrabone · 2026-10-16
- MiniCPM-V 4.7 35B-A3B hits 17+ tokens/s on iPad with ~3GB memory — techNmak · 2026-10-16
- turbopixel: layer-and-mask generative compositing runs a 9B model on 4GB GPU — 3unjee · 2026-10-16